Gaussian Processes for Advanced Motion Control

Maurice Poot; Jim Portegies; Noud Mooren; Max van Haren; Max van Meer; Tom Oomen

doi:10.1541/ieejjia.21011492

Gaussian Processes for Advanced Motion Control

Maurice Poot^*, Jim Portegies, Noud Mooren, Max van Haren, Max van Meer, Tom Oomen

^*Corresponding author for this work

Team Jan-Willem van Wingerden

Research output: Contribution to journal › Article › Scientific › peer-review

1 Citation (Scopus)

8 Downloads (Pure)

Abstract

Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.

Original language	English
Pages (from-to)	396-407
Journal	IEEJ Journal of Industry Applications
Volume	11
Issue number	3
DOIs	https://doi.org/10.1541/ieejjia.21011492
Publication status	Published - 2022

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

feedforward control
gaussian processes
learning control

Access to Document

10.1541/ieejjia.21011492

ArticleFinal published version, 29.9 MB

Cite this

@article{dec928cfd6784af0a32ec4dd7e13232e,

title = "Gaussian Processes for Advanced Motion Control",

abstract = "Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.",

keywords = "feedforward control, gaussian processes, learning control",

author = "Maurice Poot and Jim Portegies and Noud Mooren and {van Haren}, Max and {van Meer}, Max and Tom Oomen",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2022",

doi = "10.1541/ieejjia.21011492",

language = "English",

volume = "11",

pages = "396--407",

journal = "IEEJ Journal of Industry Applications",

issn = "2187-1094",

publisher = "The Institute of Electrical Engineers of Japan",

number = "3",

}

TY - JOUR

T1 - Gaussian Processes for Advanced Motion Control

AU - Poot, Maurice

AU - Portegies, Jim

AU - Mooren, Noud

AU - van Haren, Max

AU - van Meer, Max

AU - Oomen, Tom

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.

AB - Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.

KW - feedforward control

KW - gaussian processes

KW - learning control

UR - http://www.scopus.com/inward/record.url?scp=85130095439&partnerID=8YFLogxK

U2 - 10.1541/ieejjia.21011492

DO - 10.1541/ieejjia.21011492

M3 - Article

AN - SCOPUS:85130095439

VL - 11

SP - 396

EP - 407

JO - IEEJ Journal of Industry Applications

JF - IEEJ Journal of Industry Applications

SN - 2187-1094

IS - 3

ER -

Gaussian Processes for Advanced Motion Control

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this